© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107246
    Prev
    Next
    INDEX
    Explanations

    long term or estate agent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    1.48
    ad
    1.24
     on
    1.21
     is
    1.16
     an
    1.16
    c
    1.11
    ش
    1.11
    ב
    1.11
     up
    1.07
    ক
    1.07
    POSITIVE LOGITS
     दैट
    0.93
    ようになりました
    0.83
    rijke
    0.83
    lıkla
    0.82
    менение
    0.81
    дцать
    0.80
    ità
    0.79
    beitet
    0.78
    rivate
    0.77
     لکھنے
    0.76
    Activations Density 0.014%

    No Known Activations